gpu4.pics
data via LocalScore
NVIDIA RTX A6000
48 GB VRAM NVIDIA 300 W TDP
running Qwen2.5 14B Instruct· Q4_K_M· 14.8B
52
tokens / sec
521 · Strong #18 of 373
Generation
52tok/s
higher is better
Prompt / prefill
1,883tok/s
higher is better
Time to first token
692 ms
lower is better
Composite score
521
Model size
14.8B
Runtime
—
All benchmarks on this rig
| Model | Quant | Gen | Prompt | TTFT | Power | Perf/W | $/Mtok | Score |
|---|---|---|---|---|---|---|---|---|
| Qwen2.5 14B Instruct14.8B | Q4_K_M | 52 | 1,883 | 692 ms | — | — | — | 521 |